~ / rigs / niklasrichardson / ai-tooling

niklasrichardson/ai-tooling

Instructions, a starter kit, a skill and subagents for Claude Code, Codex, Claude and ChatGPT: short, structured, honest replies and multi-session work.

↗ GitHub ★ 1 MIT updated 19d ago project Claude CodeCodex
stack: Python
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~4.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 5/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit niklasrichardson/ai-tooling/agents ./rig-ai-tooling/agents
$ npx degit niklasrichardson/ai-tooling/skills ./rig-ai-tooling/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit niklasrichardson/ai-tooling/skills/handoff .claude/skills/handoff
$ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/niklasrichardson/ai-tooling/main/agents/claude-code/coder.md
$ curl -fsSL --create-dirs -o .claude/agents/explore.md https://raw.githubusercontent.com/niklasrichardson/ai-tooling/main/agents/claude-code/explore.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/niklasrichardson/ai-tooling/main/agents/claude-code/researcher.md
$ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/niklasrichardson/ai-tooling/main/agents/roles/coder.md
$ curl -fsSL --create-dirs -o .claude/agents/explore.md https://raw.githubusercontent.com/niklasrichardson/ai-tooling/main/agents/roles/explore.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/niklasrichardson/ai-tooling/main/agents/roles/researcher.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Skills (1)

Subagents (6)

coder
model: opus
Writes or changes code, debugs, and does design or architecture work. Use for any subagent task that edits code or makes technical design decisions.
Explore
model: haiku
Read-only search agent for file search, lookups and bulk extraction. Use when answering means sweeping many files, directories or logs and only the conclusion is needed. Specify breadth: \"quick\", \"
researcher
model: sonnet
Researches questions, reads documentation, summarises long material, and reviews text. Use for read-and-report work that does not change code.
coderWrites or changes code, debugs, and does design or architecture work. Use for any subagent task that edits code or makes technical design decisions.
exploreRead-only search agent for file search, lookups and bulk extraction. Use when answering means sweeping many files, directories or logs and only the conclusion is needed. Specify breadth: "quick", "med
researcherResearches questions, reads documentation, summarises long material, and reviews text. Use for read-and-report work that does not change code.

Similar rigs

copied ✓